{ "data_id": "38718", "name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3553", "exact_name": "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3553", "version": 12, "version_label": null, "description": "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3553 (TID: 12694), and it has 862 rows and 69 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied.", "format": "ARFF", "uploader": "Noureddin Sadawi", "uploader_id": 62, "visibility": "public", "creator": "\"Dr Jeremy Besnard, Dr Ivan Olier, Dr Noureddin Sadawi, Dr Larisa Soldatova, Dr Crina Grosan, Prof Ross King, Dr Richard Bickerton, Prof Andrew Hopkins and Dr Willem van Hoorn\"", "contributor": null, "date": "2016-07-16 05:14:26", "update_comment": null, "last_update": "2016-07-16 05:14:26", "licence": "Public", "status": "deactivated", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3650051\/data_53538.arff", "default_target_attribute": "pXC50", "row_id_attribute": "molecule_id", "ignore_attribute": null, "runs": 2, "suggest": { "input": [ "QSAR-DATASET-FOR-DRUG-TARGET-CHEMBL3553", "This dataset contains QSAR data (from ChEMBL version 17) showing activity values (unit is pseudo-pCI50) of several compounds on drug target ChEMBL_ID: CHEMBL3553 (TID: 12694), and it has 862 rows and 69 features (not including molecule IDs and class feature: molecule_id and pXC50). The features represent Molecular Descriptors which were generated from SMILES strings. Missing value imputation was applied to this dataset (By choosing the Median). Feature selection was also applied. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 862, "NumberOfFeatures": 71, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 70, "NumberOfSymbolicFeatures": 1, "Quartile3AttributeEntropy": null, "MaxKurtosisOfNumericAtts": 131.76463502264193, "MinMeansOfNumericAtts": -0.06357424593967519, "PercentageOfInstancesWithMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 2.8401910057455577, "MaxMeansOfNumericAtts": 42091.09628770301, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3MeansOfNumericAtts": 10.725321925754061, "MaxMutualInformation": null, "MinNominalAttDistinctValues": null, "PercentageOfNumericFeatures": 98.59154929577466, "Quartile3MutualInformation": null, "MaxNominalAttDistinctValues": null, "MinSkewnessOfNumericAtts": -2.0955437938091293, "PercentageOfSymbolicFeatures": 1.4084507042253522, "Quartile3SkewnessOfNumericAtts": 1.369745561436628, "MaxSkewnessOfNumericAtts": 10.46283471821633, "MinStdDevOfNumericAtts": 0.005799023593481698, "Quartile1AttributeEntropy": null, "Quartile3StdDevOfNumericAtts": 5.708171893728901, "MaxStdDevOfNumericAtts": 83447.93762344458, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.0326666903236873, "StdvNominalAttDistinctValues": null, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 0.38155597447795814, "MeanKurtosisOfNumericAtts": 5.199070512178398, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 627.7831403215113, "Quartile1SkewnessOfNumericAtts": 0.05969451536373778, "AutoCorrelation": 0.5802915214866435, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.223228211134999, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.08236658932714618, "MeanNominalAttDistinctValues": null, "Quartile2KurtosisOfNumericAtts": 0.7520111386539989, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.9133885214635814, "Quartile2MeansOfNumericAtts": 2.114849187935036, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 1202.81830817813, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.6137460501683712, "Quartile2StdDevOfNumericAtts": 0.5368958084160662, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7658675934412806, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "tag": "MetaQSAR", "uploader": "62" }, { "tag": "study_13", "uploader": "62" } ], "features": [ { "name": "pXC50", "index": "70", "type": "numeric", "distinct": "151", "missing": "0", "target": "1", "min": "5", "max": "9", "mean": "6", "stdev": "1" }, { "name": "molecule_id", "index": "0", "type": "nominal", "distinct": "862", "missing": "0", "identifier": "1", "distr": [] }, { "name": "Rbrid", "index": "1", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "10", "mean": "1", "stdev": "2" }, { "name": "RFD", "index": "2", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "TRS", "index": "3", "type": "numeric", "distinct": "36", "missing": "0", "min": "6", "max": "52", "mean": "24", "stdev": "7" }, { "name": "SdsCH", "index": "4", "type": "numeric", "distinct": "123", "missing": "0", "min": "0", "max": "5", "mean": "0", "stdev": "1" }, { "name": "nCIR", "index": "5", "type": "numeric", "distinct": "19", "missing": "0", "min": "1", "max": "81", "mean": "6", "stdev": "6" }, { "name": "MATS1m", "index": "6", "type": "numeric", "distinct": "178", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "H.047", "index": "7", "type": "numeric", "distinct": "32", "missing": "0", "min": "0", "max": "31", "mean": "12", "stdev": "6" }, { "name": "Eig05_EA.dm.", "index": "8", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "JGT", "index": "9", "type": "numeric", "distinct": "275", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Chi1_EA.dm.", "index": "10", "type": "numeric", "distinct": "731", "missing": "0", "min": "0", "max": "77", "mean": "25", "stdev": "14" }, { "name": "GATS1p", "index": "11", "type": "numeric", "distinct": "453", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "NdsCH", "index": "12", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "JGI4", "index": "13", "type": "numeric", "distinct": "46", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMAD_AEA.ed.", "index": "14", "type": "numeric", "distinct": "199", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "SssO", "index": "15", "type": "numeric", "distinct": "326", "missing": "0", "min": "0", "max": "24", "mean": "4", "stdev": "6" }, { "name": "GATS2m", "index": "16", "type": "numeric", "distinct": "414", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "MATS1p", "index": "17", "type": "numeric", "distinct": "292", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "NssCH2", "index": "18", "type": "numeric", "distinct": "14", "missing": "0", "min": "0", "max": "16", "mean": "3", "stdev": "3" }, { "name": "Eig06_EA.dm.", "index": "19", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SsssN", "index": "20", "type": "numeric", "distinct": "237", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "IVDE", "index": "21", "type": "numeric", "distinct": "289", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "MATS1i", "index": "22", "type": "numeric", "distinct": "402", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "GATS2e", "index": "23", "type": "numeric", "distinct": "536", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS7e", "index": "24", "type": "numeric", "distinct": "677", "missing": "0", "min": "1", "max": "6", "mean": "5", "stdev": "1" }, { "name": "C.016", "index": "25", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "SpMin7_Bh.s.", "index": "26", "type": "numeric", "distinct": "366", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "ATS6i", "index": "27", "type": "numeric", "distinct": "665", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "C.006", "index": "28", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "2" }, { "name": "NssO", "index": "29", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "ATS7i", "index": "30", "type": "numeric", "distinct": "668", "missing": "0", "min": "1", "max": "6", "mean": "5", "stdev": "1" }, { "name": "Eig04_EA.dm.", "index": "31", "type": "numeric", "distinct": "49", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "GATS1i", "index": "32", "type": "numeric", "distinct": "497", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATSC7m", "index": "33", "type": "numeric", "distinct": "841", "missing": "0", "min": "0", "max": "78", "mean": "24", "stdev": "12" }, { "name": "ATS6e", "index": "34", "type": "numeric", "distinct": "660", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATSC6v", "index": "35", "type": "numeric", "distinct": "832", "missing": "0", "min": "1", "max": "35", "mean": "11", "stdev": "5" }, { "name": "ATSC2m", "index": "36", "type": "numeric", "distinct": "791", "missing": "0", "min": "1", "max": "39", "mean": "17", "stdev": "7" }, { "name": "C.032", "index": "37", "type": "numeric", "distinct": "3", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "P_VSA_LogP_7", "index": "38", "type": "numeric", "distinct": "103", "missing": "0", "min": "31", "max": "506", "mean": "193", "stdev": "84" }, { "name": "P_VSA_p_1", "index": "39", "type": "numeric", "distinct": "116", "missing": "0", "min": "24", "max": "530", "mean": "209", "stdev": "85" }, { "name": "SpMaxA_EA.ed.", "index": "40", "type": "numeric", "distinct": "313", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "SpMin7_Bh.m.", "index": "41", "type": "numeric", "distinct": "438", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "ATS2e", "index": "42", "type": "numeric", "distinct": "577", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "nCsp3", "index": "43", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "18", "mean": "4", "stdev": "3" }, { "name": "ATS5i", "index": "44", "type": "numeric", "distinct": "650", "missing": "0", "min": "3", "max": "6", "mean": "5", "stdev": "0" }, { "name": "ATS2i", "index": "45", "type": "numeric", "distinct": "588", "missing": "0", "min": "4", "max": "5", "mean": "5", "stdev": "0" }, { "name": "IAC", "index": "46", "type": "numeric", "distinct": "708", "missing": "0", "min": "27", "max": "166", "mean": "78", "stdev": "20" }, { "name": "TIC0", "index": "47", "type": "numeric", "distinct": "708", "missing": "0", "min": "27", "max": "166", "mean": "78", "stdev": "20" }, { "name": "ATSC6p", "index": "48", "type": "numeric", "distinct": "825", "missing": "0", "min": "1", "max": "27", "mean": "9", "stdev": "4" }, { "name": "Chi1_EA.bo.", "index": "49", "type": "numeric", "distinct": "734", "missing": "0", "min": "4", "max": "22", "mean": "12", "stdev": "3" }, { "name": "Wap", "index": "50", "type": "numeric", "distinct": "718", "missing": "0", "min": "1056", "max": "1325540", "mean": "42091", "stdev": "83448" }, { "name": "GATS1v", "index": "51", "type": "numeric", "distinct": "365", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "SpMin8_Bh.s.", "index": "52", "type": "numeric", "distinct": "348", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Eig03_EA.dm.", "index": "53", "type": "numeric", "distinct": "66", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "ATSC7p", "index": "54", "type": "numeric", "distinct": "825", "missing": "0", "min": "0", "max": "29", "mean": "8", "stdev": "4" }, { "name": "GATS2s", "index": "55", "type": "numeric", "distinct": "452", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Eta_B_A", "index": "56", "type": "numeric", "distinct": "34", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "SpMin8_Bh.v.", "index": "57", "type": "numeric", "distinct": "447", "missing": "0", "min": "0", "max": "2", "mean": "1", "stdev": "0" }, { "name": "P_VSA_e_1", "index": "58", "type": "numeric", "distinct": "40", "missing": "0", "min": "24", "max": "530", "mean": "202", "stdev": "85" }, { "name": "P_VSA_m_1", "index": "59", "type": "numeric", "distinct": "40", "missing": "0", "min": "24", "max": "530", "mean": "202", "stdev": "85" }, { "name": "P_VSA_s_2", "index": "60", "type": "numeric", "distinct": "68", "missing": "0", "min": "24", "max": "530", "mean": "203", "stdev": "85" }, { "name": "P_VSA_v_1", "index": "61", "type": "numeric", "distinct": "40", "missing": "0", "min": "24", "max": "530", "mean": "202", "stdev": "85" }, { "name": "P_VSA_i_3", "index": "62", "type": "numeric", "distinct": "478", "missing": "0", "min": "24", "max": "550", "mean": "251", "stdev": "93" }, { "name": "ATS1e", "index": "63", "type": "numeric", "distinct": "539", "missing": "0", "min": "3", "max": "5", "mean": "4", "stdev": "0" }, { "name": "O.059", "index": "64", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "ATSC7v", "index": "65", "type": "numeric", "distinct": "828", "missing": "0", "min": "0", "max": "37", "mean": "11", "stdev": "6" }, { "name": "nROR", "index": "66", "type": "numeric", "distinct": "4", "missing": "0", "min": "0", "max": "3", "mean": "0", "stdev": "1" }, { "name": "ATS8m", "index": "67", "type": "numeric", "distinct": "663", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "1" }, { "name": "ATS5v", "index": "68", "type": "numeric", "distinct": "641", "missing": "0", "min": "2", "max": "5", "mean": "4", "stdev": "0" }, { "name": "Eta_betaP_A", "index": "69", "type": "numeric", "distinct": "270", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }